brief
Skill2 starsChanged 3 months agoMITView on GitHub
Interactive survey across the 9 brief files. Starts with desktop-first vs mobile-first (the most important question), then niche, then the rest. Fills brief/*.md instead of the user.
81 other projects use a version of this.
Adopted by
Most recently taken up by
- noelceta/content-enginetheir own version, first seen Nov 16, 2026
- MiguelARojas3103/rtovar-aiostheir own version, first seen Nov 15, 2026
- nazmirket/skillstheir own version, first seen Nov 15, 2026
- sufficiently-advanced-ai/imitheir own version, first seen Nov 12, 2026
- grainulation/grainulatortheir own version, first seen Nov 12, 2026
- fjwood69/moritheir own version, first seen Nov 10, 2026
Used with
Projects with it also use capture, strategy and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
toneron2Skillcapture
Capture thoughts to inbox with automatic classification
Also in 6 projects that use this
EpistatesSkillstrategy
Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X presence.
Also in 4 projects that use this
aleksander-dytkoSkilldecision
Make a product decision with full context from the vault and available sources
Also in 3 projects that use this
dirienSkilldecide
Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.
Also in 5 projects that use this
JaimeGBASkillingest
Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base
Also in 7 projects that use this
howellsSkillreconcile
Audit a project against current plugin conventions and offer to update structure.
Also in 3 projects that use this
Other versions81 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 81
- anthropics/knowledge-work-plugins★ 36ksame name
- suboss87/FDEOps★ 940same name
- with-pebbly/aseprite-ai-artist★ 697same name
- educlopez/ui-craft★ 441same name
- github/lever★ 279same name
- dylanroscover/Embody★ 219same name
- yofine/skills★ 154same name
- grainulation/grainulator★ 86same name
- g2i-ai/agents★ 52same name
- gregmos/memoforge★ 38same name
71 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- animationSkill
- auditSkill
- blocksSkill
- buildSkill
- copy-analyzeSkill
- deploySkill
- design-lockSkill
- iconsSkill
- inboxSkill
- mediaSkill
- mobileSkill
- refsSkill
- tokensSkill
- typographySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. 0 are common, 7 are distinctive, and 10 are very specific to this project.
0
Common
Most of the 74 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Start of a new project (before any /build).
- Very specific: line 19
Read every brief/*.md. Determine which fields are filled, which are TBD.
- Very specific: line 34
Wait for an explicit answer.
- Distinctive: line 40
Ask one question at a time (do not batch 10 questions at once — user tires).
- Distinctive: line 41
Use checklists where preset options exist.
- Very specific: line 47
Do not accept "beauty" — narrow it to "men's Botox for CEOs 35-50 in Barcelona".
- Very specific: line 48
Do not accept "clients" — narrow maturity (cold/warm/hot).
- Very specific: line 52
If the user checked interactive blocks — offer to run /blocks immediately to configure.
- Distinctive: line 57
If TBD remain — what to ask the client.
- Distinctive: line 61
One field — one question: Do not batch.
- Distinctive: line 62
Do not guess for the user: If unclear — clarify.
- Distinctive: line 64
Save as you go: Not at the end. Otherwise if the session drops — everything's lost.
- Distinctive: line 65
Respect status: If a field is already filled — do not re-ask, only clarify if needed.
- Very specific: line 69
Do not start /design-lock until 01-business + 02-audience + 05-design are filled.
- Very specific: line 70
Do not suggest skipping 00-priority — it's critical.
- Very specific: line 71
Do not fill brief/copy-analysis.md — that's /copy-analyze.
- Very specific: line 72
Do not touch brief/blocks/*.md — that's /blocks.
“Common” is measured: kept by at least 6 in 10 of the 74 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/brief
Guides the user through the questionnaire. Fills brief/00-priority.md → brief/08-content-pipeline.md.
When to use
- Start of a new project (before any
/build). - User prefers a dialog over filling .md files by hand.
- Revising an existing brief.
Process
Step 1. Read existing files
Read every brief/*.md. Determine which fields are filled, which are TBD.
Step 2. Ask the first — most important — question
Desktop-first or mobile-first?
This decides:
- Assembly order (down or up)
- Block composition
- Reference viewport (1920px or 390px)
Help to choose: <brief decision table from 00-priority.md>Wait for an explicit answer. Save to brief/00-priority.md.
Step 3. Walk files 01-08 in order
For each file:
- List
TBDfields. - Ask one question at a time (do not batch 10 questions at once — user tires).
- Use checklists where preset options exist.
- Save the answer (Edit tool).
Step 4. Special attention — niche discovery
brief/01-business.md — niche section — critical for /copy-analyze.
Do not accept "beauty" — narrow it to "men's Botox for CEOs 35-50 in Barcelona".
Do not accept "clients" — narrow maturity (cold/warm/hot).
Step 5. After 07-interactive
If the user checked interactive blocks — offer to run /blocks immediately to configure.
Step 6. Final summary
Show brief completeness: how many fields LOCKED, how many TBD. If TBD remain — what to ask the client.
Rules of behavior
- One field — one question. Do not batch.
- Do not guess for the user. If unclear — clarify.
- Use examples. "e.g. form submission → manager calls within 2 hours".
- Save as you go. Not at the end. Otherwise if the session drops — everything's lost.
- Respect status. If a field is already filled — do not re-ask, only clarify if needed.
What NOT to do
- Do not start
/design-lockuntil01-business+02-audience+05-designare filled. - Do not suggest skipping
00-priority— it's critical. - Do not fill
brief/copy-analysis.md— that's/copy-analyze. - Do not touch
brief/blocks/*.md— that's/blocks.
Next
Once done:
- Suggest
/inbox(if the client already has materials) or wait for materials. - Or
/refs(if references are already inreferences/).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

